A fault diagnosis model for the power transformer based on the enhanced association rule mining algorithm

The association rule mining methods are commonly utilized to analyze the dissolved gas which is applied to diagnose the power transmission fault events. For the purpose of further improving the performance, this paper proposes a diagnosis method for power transformer fault events based on the enhanced association rule mining model. Firstly, the conditional and adjustable significance measurements are deployed to assess the different input features, and to incorporate the high impact low probability data. Thus, all the potential extreme circumstances in reality can be considered. Next, the risk weights of input features are generated through their likelihood of causing a fault rather than their statistical distribution. Therefore, the impact of each feature can be measured more precisely. Finally, the Relim algorithm is applied to raise the efficiency of data mining. The consequences of the empirical study show that the proposed method is more pinpoint, realizable and efficient compared with the methods with the fixed significance measurements, the conventional risk weight estimator, and the Apriori algorithm.